Abstract
Using a risk matrix for Risk mapping constitutes the basis of risk management strategy. It aims to classify the identified risks with regards to their management and control. This risk classification, which is based on the frequency and the severity dimensions, is often carried out according to a procedure founded on experts’ judgments. In order to overcome the subjectivity bias of this classification, this paper presents the contribution of the Principal Components Analysis (PCA) method: an exploratory method for graphing risks based on factors that allow a better visualized classification of scenarios accidents. Still, the commonly encountered problem in the data classified by the PCA method resides in the main factors of classification; we judged useful to frame these letters by an algebraic formulation to make an improvement of this classification possible. The obtained results show that the suggested method is a promising alternative to solve the recurring problems of risk matrices, notably in accident scenarios’ classification.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
American Institute of Chemical Engineers (AICE) (1992) Guidelines for hazard evaluation procedures, 2nd edn. New York
American Institute of Chemical Engineers (AICE) (1995) Tools for making acute risk decisions. New York
Barshan E, Ghodsi A, Azimifar Z, Jahromi MZ (2011) ,”Supervised principal component analysis: visualization, classification and regression on subspaces and sub-manifolds”. Pattern Recogn 44(7):1357–1371
Baybutt P (2014) The use of risk matrices and risk graphs for SIL determination. Process Saf Prog 33(2):179–182
Baybutt P (2016) Guidelines for designing risk matrices. Process Saf Prog 37(1):41–46
CCPS (2000) Guidelines for chemical process quantitative risk analysis, 2nd edn. Wiley, New York
Da Cunha SB (2016) A review of quantitative risk assessment of onshore pipelines. J Loss Prev Process Ind 44(11):282–298
Dejan R (2013) Atool for risk assessment. Saf Eng 3(3):121–127
Duijm NJ (2015) Recommendations on the use and design of risk matrices. Saf Sci 76:21–31
Ferjencik M (2004) The role of the two-phase scenarios concept in the matrix relative risk ranking procedure. Process Saf Prog 16(2):117–120
Fang L, Xiao B, Yu H, You Q (2018) A stable systemic risk ranking in China’s banking sector: based on principal component analysis. Phys A 492:1997–2009
Gul M, Guneri AF (2016) A fuzzy multi criteria risk assessment based on decision matrix technique: a case study for aluminum industry. J Loss Prev Process Ind 40(3):89–100
Gupta A, Barbu A (2018) Parameterized principal component analysis. Pattern Recognit 78:215–227
Hair J, Anderson R, Tatham R, Black W (1998) Multivariate data analysis. 5th Prentice Hall International, London
He L, Chen Y, Liu LY (2013) A risk matrix approach based on clustering algorithm. J Appl Sci 13(20):4188–4194
Huihui N, Chen A, Chen N (2010) Some extensions on risk matrix approach. Saf Sci 48(10):1269–1278
ISO 31000:2009 (2009) Risk management—principles and guidelines. ISO 31000:2009, International Organization for Standardization, Geneva
Jolliffe LT (1986) Principal component analysis. Springer, New York
Jung S, Ng D, Laird CD, Sam Mannan M (2010) A new approach for facility siting using mapping risks on a plant grid area and optimization. J Loss Prev Process Ind 23:824–830
LRET (LLOYD’S Register Energy and Transport) (2007) A severe accident analysis report of the industrial group “Total—Sonatarch—Repsol. Report ABN0961615/01 REV.04, realized by LLOYD’S Register EMEA Group Energy and Transport
Manwendra K, Tripathi PP, Chatto P, Ganguly S (2015) Multivariate analysis and classification of bulk metallic glasses using principal component analysis. Comput Mater Sci 107:79–87
Marhavilas PK, Koulouriotis D, Gemeni V (2011) Risk analysis and assessment methodologies in the work sites: on a review, classification and comparative study of the scientific literature of the period 2000–2009. J Loss Prev Process Ind 24(5):477–523
Merad M (2004) Analyse de l’état de l’art sur les grilles de criticité. INERIS report, France, DRA–D38
Moore DA (2004) The use of a ranking matrix and recommendation prioritization system for process hazard analysis studies. Process Saf Prog 16(2):83–85
Palese LL (2018) A random version of principal component analysis in data clustering. Comput Biol Chem 73(4):57–64
Peeters W, Peng Z (2015) An approach towards global standardization of the risk matrix. J Space Saf Eng 2(1):31–38
Penkova TG (2017) Principal component analysis and cluster analysis for evaluating the natural and anthropogenic territory safety. Proc Comput Sci 112:99–108
Reniers G-L-L, Dullaert W, Ale B-J-M, Soudan K (2005) Developing an external domino accident prevention framework: Hazwim. J Loss Prev Process Ind 18(3):127–138
Ringnér M (2008) “What is principal component analysis? “Nat Biotechnol 26(3):303–304
Ng SC (2017) Principal component analysis to reduce dimension on digital image. Proc Comput Sci 111:113–119
Schmidt MS (2016) Making sense of risk tolerance criteria. J Loss Prev Process Ind 41(5):344–354
Tixier J, Dusserre G, Salvi O, Gaston D (2002) Review of 62 risk analysis methodologies of industrial plants. J Loss Prevent Process Ind 15(4):291–303
Villeneuve E (2012) Hybridization of the cognitive and static experience feedbacks for risks assessment. PhD thesis presented at the University of Toulouse, France
Zhu Q, Kuang X, Shen Y (2003) Risk matrix method and its application in the field of technical project risk management. Eng Sci 5(1):89–94
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hadef, H., Djebabra, M. Proposal method for the classification of industrial accident scenarios based on the improved principal components analysis (improved PCA). Prod. Eng. Res. Devel. 13, 53–60 (2019). https://doi.org/10.1007/s11740-018-0859-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11740-018-0859-3